Speech synthesis techniques. A survey
The DOI matches its Crossref record; 16 of the 18 references it cites were found in a registry or an index.
Abstract
The goal of this paper is to provide a short but a comprehensive overview of Text-To-Speech synthesis by highlighting its digital signal processing component. First two rule-based synthesis techniques (formant synthesis and articulatory synthesis) are explained then the concatenative synthesis is explored. Concatenative synthesis is simpler than rule-based synthesis, since there is no need to determine speech production rules. However, it introduces the challenges of prosodic modification to speech units and resolving discontinuities at unit boundaries. Prosodic modification results in artifacts in the speech that make the speech sound unnatural. Unit selection synthesis, which is a kind of concatenative synthesis, solves this problem by storing numerous instances for each unit with varying prosodies. The unit that best matches the target prosody is selected and concatenated. To resolve mismatches speech synthesis system combines the unit-selection method with Harmonic plus Noise Model (HNM). This model represents speech signal as a sum of a harmonic and noise part. The decomposition of speech signal into these two parts enables more natural sounding modifications of the signal. Finally Hidden Markov model(HMM) synthesis combined with an HNM model is introduced in order to obtain a Text-To-Speech system that requires smaller development time and cost.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“However, the output produced this way often lacked human-like naturalness, resulting in mechanical or “robotic” sound [39].”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [39]
Citations
Cites
Review of text-to-speech conversion for English
Klatt, D. H. (1987) · The Journal of the Acoustical Society of America · doi:10.1121/1.395275 · Cited by 802 · cited 2×
“However we do not yet know the optimal rule to do this [3].”
BackgroundFrom text to speech: the MITalk system
Allen, J., Hunnicutt, M. S., Klatt, D. H., Armstrong, R. C., & Pisoni, D. B. (1987) · Cited by 405
Stylianou, Y. (1996) · Medical Entomology and Zoology · Cited by 235
From text to speech: The MITalk system
Holmes, J. N. (1987) · Computer Speech & Language · doi:10.1016/0885-2308(87)90017-9 · Cited by 164
Hidden semi-Markov model based speech synthesis
Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., & Kitamura, T. (2004) · Interspeech (USB) · doi:10.21437/interspeech.2004-460 · Cited by 150 · cited 1×
“The modeling accuracy can be improved by using hidden semi-Markov models (HSMMs) [13], trajectory HMMs [14], and stochastic Markov graphs [15].”
MethodApplications of voice processing to telecommunications
Rabiner, L. R. (1994) · Proceedings of the IEEE · doi:10.1109/5.265347 · Cited by 80
The klattalk text-to-speech conversion system
Klatt, D. H. (2005) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1982.1171431 · Cited by 77 · cited 1×
“The formant synthesis approach has been implemented in MITalk [4, 5], in KlatTalk [6], and in DECTalk [7].”
MethodRare Events and Closed Domains: Two Delicate Concepts in Speech Synthesis
Möbius, B. (2003) · International Journal of Speech Technology · doi:10.1023/a:1021052023237 · Cited by 62 · cited 1×
“This phenomenon of unseen contexts may well never be fully overcome with concatenative synthesis as [10] suggest that rare events will always occur in language.”
BackgroundHigh-quality text-to-speech synthesis : an overview
Dutoit, T. (1997) · Cited by 61
An introduction of trajectory model into HMM-based speech synthesis.
Zen, H., Tokuda, K., & Kitamura, T. (2004) · Cited by 59
Research works printed but not linked: 2
- kroger, 1992, Minimal Rules for Articulatory Speech Synthesis, Proceedings of EUSIPC092, 331
- klatt, 1990, Dec Talk user's manual, Digital Equipment Corporation
Cited by
A survey on neural speech synthesis
Tan, X., Qin, T., Soong, F., & Liu, T.-Y. (2021) · arXiv · doi:10.48550/arxiv.2106.15561 · Cited by 216
“While there are multiple survey papers on statistical parametric speech synthesis [27, 418, 351, 415] and neural TTS [325, 220, 300, 242, 115, 254, 236], a comprehensive survey on the basics and the recent developments of neural TTS is still necessary since the topics in this area are diverse and evolve quickly.”
BackgroundA Review on Human-Computer Interaction and Intelligent Robots
Ren, F., & Bao, Y. (2019) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622019300052 · Cited by 163
Conventional and contemporary approaches used in text to speech synthesis: a review
Kaur, N., & Singh, P. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10315-0 · Cited by 139
“The task of back end of TTS (Waveform Synthesis Module) is to artificially synthesize the speech waveforms from the symbolic input linguistic vector (Tabet and Boughazi 2011; Sasirekha and Chandra 2012).”
MethodAudio Deepfake Detection: What Has Been Achieved and What Lies Ahead
Zhang, B., Cui, H., Nguyen, V., & Whitty, M. (2025) · Sensors · doi:10.3390/s25071989 · Cited by 72
“However, the output produced this way often lacked human-like naturalness, resulting in mechanical or “robotic” sound [39].”
Deepfakes as a threat to a speaker and facial recognition: An overview of tools and attack vectors
Firc, A., Malinka, K., & Hanáček, P. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e15090 · Cited by 80
Metadata
- Authors
- Tabet, Y., & Boughazi, M.
- Affiliations
- University of Boumerdes (DZ)
- Badji Mokhtar-Annaba University (DZ)
- Venue
- International Workshop on Systems, Signal Processing and their Applications, WOSSPA
- Publisher
- IEEE
- Published
- 2011-05
- Pages
- 67-70
- OpenAlex
- W2102737569
- Cited by
- 78
- References
- 18
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 8 · 2022: 7 · 2021: 5 · 2020: 5 · 2019: 5 · 2018: 5 · 2017: 4 · 2016: 6 · 2015: 11 · 2014: 8 · 2013: 5 · 2012: 1
- FWCI
- 3.51
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Workshop on Systems, Signal Processing and their Applications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Keywords
- text-to-speech, rule-based synthesis, formant synthesis, articulatory speech synthesis, concatenative synthesis, unit selection, prosodic modification, harmonic plus noise model, speech production
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Speech synthesis techniques. A survey. https://app.cochat.ai/papers/10.1109/wosspa.2011.5931414
- The paper
- Tabet, Y., & Boughazi, M. (2011). Speech synthesis techniques. A survey. International Workshop on Systems, Signal Processing and their Applications, WOSSPA. https://doi.org/10.1109/wosspa.2011.5931414
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.